# OpenAI内部模型名称意外泄露

- 来源：TestingCatalog News 🗞 (@testingcatalog)
- 发布时间：2026-04-22 18:03
- AIHOT 分数：56
- AIHOT 链接：https://aihot.virxact.com/items/cmo9welli050gsls2g35vcfyi
- 原文链接：https://x.com/testingcatalog/status/2046892580449693711

## AI 摘要

OPENAI 🚨: GPT-5.5 和一系列内部模型名称最近在 Codex 上被发现，这通常意味着 OpenAI 正准备发布一个新模型。

- oai-2.1
- arcanine
- glacier-alpha
- glacier-alpha-block-cy4
- glacier-alpha-block-cy3

很快 👀

致谢 @TheAhmadOsman

## 正文

OPENAI 🚨： GPT-5.5 and a bunch of internal model names have been spotted on Codex recently， and this normally signals that OpenAI is preparing to release a new model.

- oai-2.1
- arcanine
- glacier-alpha
- glacier-alpha-block-cy4
- glacier-alpha-block-cy3

Soon 👀

h/t @TheAhmadOsman

### 引用推文

> can：🚨 OpenAI just accidentally leaked all the internal models in Codex model picker Seem to be only on pro accounts